mjpsm's picture
Use prebuilt CPU wheel for llama-cpp-python (source build OOMs)
aae1c11 verified
Raw History Blame Contribute Delete
584 Bytes
FROM python:3.11-slim
ENV PYTHONDONTWRITEBYTECODE=1
ENV PYTHONUNBUFFERED=1
ENV PIP_NO_CACHE_DIR=1
RUN apt-get update \
&& apt-get install -y --no-install-recommends libgomp1 \
&& rm -rf /var/lib/apt/lists/*
WORKDIR /app
COPY requirements.txt /app/requirements.txt
RUN pip install --upgrade pip \
&& pip install --prefer-binary \
--extra-index-url https://abetlen.github.io/llama-cpp-python/whl/cpu \
-r /app/requirements.txt
COPY main.py /app/main.py
EXPOSE 7860
CMD ["uvicorn", "main:app", "--host", "0.0.0.0", "--port", "7860", "--workers", "1"]